Ross ROSS = Recommend OSS · open-source software intelligence for agents

vdaas/vald

Vald. A Highly Scalable Distributed Vector Search Engine observed · 2026-08-28

github.com/vdaas/vald · homepage · Go · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

91/100

  • Activity 99
  • Release rhythm 75
  • Longevity 100
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: 123.0
  • age_days: 2614
  • days_rel: 7
  • days_push: 7
  • n_releases_24m: 5

Full methodology

Adoption not part of the score

1718 stars · 95 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Vald is a highly scalable, distributed approximate nearest neighbor (ANN) dense vector search engine built on cloud-native architecture and the NGT algorithm. It runs on Kubernetes with automatic vector indexing, index backup, replication, and horizontal scaling designed for searching billions of feature vectors.

Use cases

  • search billions of vectors for nearest neighbors
  • build an image similarity search service
  • power semantic text search with BERT embeddings
  • deploy a scalable vector database on Kubernetes
  • recommend similar products based on embeddings
  • deduplicate images or videos by vector similarity
  • back up and replicate vector indexes for disaster recovery
  • query a vector search engine via gRPC or REST

When to choose

  • you need a distributed, horizontally scalable ANN engine for billions of vectors
  • your infrastructure is Kubernetes-based and you want cloud-native deployment via Helm
  • you need automatic indexing, backup, and replica rebalancing without stop-the-world indexing
  • you want gRPC and REST APIs with official Go, Java, Python, and Node.js SDKs

When to avoid

  • you don't run Kubernetes and just need a simple embedded vector store
  • your dataset is small enough for a single-node library like FAISS or Annoy
  • you need a fully managed vector database service rather than self-hosted infrastructure
  • you want a lightweight in-process ANN library instead of a distributed microservice cluster

Facets

service · maturity active

vector-database search-engine rpc deployment microservices sdk machine-learning databases cloud-computing microservices computer-vision go cloud self-hosted approximate-nearest-neighbor ann ngt vector-search similarity-search helm-chart grpc-api distributed-indexing image-search cncf-landscape search containers natural-language-processing kubernetes docker web-server

9 sources

Member repositories

RepositoryRoleHealth v2
vdaas/valdmain91

For agents

markdown · JSON · MCP: product_card(name="vdaas/vald")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem